mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-19 12:58:14 +00:00
apify_actors -> apify_actors_tool, refactor readme
This commit is contained in:
MQ
@@ -1,5 +1,5 @@
|
||||
from .ai_mind_tool.ai_mind_tool import AIMindTool
|
||||
from .apify_actors.apify_actors import ApifyActorsTool
|
||||
from .apify_actors_tool.apify_actors_tool import ApifyActorsTool
|
||||
from .brave_search_tool.brave_search_tool import BraveSearchTool
|
||||
from .browserbase_load_tool.browserbase_load_tool import BrowserbaseLoadTool
|
||||
from .code_docs_search_tool.code_docs_search_tool import CodeDocsSearchTool
|
||||
|
||||
@@ -1,101 +0,0 @@
|
||||
# ApifyActorsTool
|
||||
|
||||
Integrate [Apify Actors](https://apify.com/) into your CrewAI workflows with ease.
|
||||
|
||||
## Description
|
||||
|
||||
The `ApifyActorsTool` seamlessly integrates [Apify Actors](https://apify.com/) - cloud-based web scraping and automation programs—into your CrewAI workflows. Whether you need to extract data, crawl websites, or automate tasks, this tool simplifies the process without requiring infrastructure management.
|
||||
|
||||
Key features:
|
||||
- **Run Actors Directly**: Execute Actors like the [RAG Web Browser](https://apify.com/apify/rag-web-browser) within CrewAI agents.
|
||||
- **Real-Time Data**: Ideal for tasks requiring up-to-date web data or automation.
|
||||
- **Explore More**: Discover additional Actors in the [Apify Store](https://apify.com/store).
|
||||
|
||||
For detailed integration guidance, see the [Apify CrewAI documentation](https://docs.apify.com/platform/integrations/crewai).
|
||||
|
||||
## Installation
|
||||
|
||||
To use `ApifyActorsTool`, install the required packages and configure your Apify API token. You’ll need an API token from Apify - see the [Apify API documentation](https://docs.apify.com/platform/integrations/api) for instructions.
|
||||
|
||||
### Steps
|
||||
|
||||
1. **Install Dependencies**
|
||||
Use pip to install `crewai[tools]` and `langchain-apify`:
|
||||
```bash
|
||||
pip install 'crewai[tools]' langchain-apify
|
||||
```
|
||||
Alternatively, with `uv`:
|
||||
```bash
|
||||
uv pip install 'crewai[tools]' langchain-apify
|
||||
```
|
||||
|
||||
2. **Set Your API Token**
|
||||
Export the token as an environment variable:
|
||||
- On Linux/macOS:
|
||||
```bash
|
||||
export APIFY_API_TOKEN='your-api-token-here'
|
||||
```
|
||||
- On Windows (Command Prompt):
|
||||
```cmd
|
||||
set APIFY_API_TOKEN=your-api-token-here
|
||||
```
|
||||
- Or add it to your `.env` file and load it with a library like `python-dotenv`.
|
||||
|
||||
3. **Verify Installation**
|
||||
Run `python -c "import langchain_apify; print('Setup complete')"` to ensure dependencies are installed.
|
||||
|
||||
## Usage example
|
||||
|
||||
Here’s how to use `ApifyActorsTool` to run the [RAG Web Browser Actor](https://apify.com/apify/rag-web-browser) for web searching within a CrewAI workflow:
|
||||
|
||||
```python
|
||||
from crewai_tools import ApifyActorsTool
|
||||
|
||||
# Initialize the tool with an Apify Actor
|
||||
tool = ApifyActorsTool(actor_name="apify/rag-web-browser")
|
||||
|
||||
# Run the tool with input parameters
|
||||
results = tool.run(run_input={"query": "What is CrewAI?", "maxResults": 5})
|
||||
|
||||
# Process the results
|
||||
for result in results:
|
||||
print(f"URL: {result['metadata']['url']}")
|
||||
print(f"Content: {result.get('markdown', 'N/A')[:100]}...") # Snippet of markdown content
|
||||
```
|
||||
|
||||
### Expected output
|
||||
|
||||
```text
|
||||
URL: https://www.example.com/crewai-intro
|
||||
Content: CrewAI is a framework for building AI-powered workflows...
|
||||
URL: https://docs.crewai.com/
|
||||
Content: Official documentation for CrewAI...
|
||||
```
|
||||
|
||||
For a more comprehensive example with tool-agent, see [CrewAI Apify Actor template](https://apify.com/templates/python-crewai).
|
||||
|
||||
Try other Actors from the [Apify Store](https://apify.com/store) by changing `actor_name` and adjusting `run_input` per the Actor's input schema.
|
||||
|
||||
## Configuration
|
||||
|
||||
The `ApifyActorsTool` requires specific inputs to operate:
|
||||
|
||||
- **`actor_name` (str, required)**
|
||||
The ID of the Apify Actor to run (e.g., `"apify/rag-web-browser"`). Find Actors in the [Apify Store](https://apify.com/store).
|
||||
- **`run_input` (dict, required at runtime)**
|
||||
A dictionary of input parameters for the Actor. Examples:
|
||||
- For `apify/rag-web-browser`: `{"query": "search term", "maxResults": 5}`
|
||||
- Check each Actor’s [input schema](https://apify.com/apify/rag-web-browser/input-schema) for details.
|
||||
|
||||
The tool adapts dynamically to the chosen [Actor](https://docs.apify.com/platform/actors).
|
||||
|
||||
## Resources
|
||||
|
||||
- **[Apify Platform](https://apify.com/)**: Explore the Apify ecosystem.
|
||||
- **[RAG Web Browser Actor](https://apify.com/apify/rag-web-browser)**: Try this popular Actor for web data retrieval.
|
||||
- **[Apify Actors Documentation](https://docs.apify.com/platform/actors)**: Learn how to use and create Actors.
|
||||
- **[CrewAI Integration Guide](https://docs.apify.com/platform/integrations/crewai)**: Official guide for Apify and CrewAI.
|
||||
|
||||
---
|
||||
|
||||
Streamline your CrewAI workflows with `ApifyActorsTool` - combine the power of Apify’s web scraping and automation with agent-based intelligence.
|
||||
86
src/crewai_tools/tools/apify_actors_tool/README.md
Normal file
86
src/crewai_tools/tools/apify_actors_tool/README.md
Normal file
@@ -0,0 +1,86 @@
|
||||
# ApifyActorsTool
|
||||
|
||||
Integrate [Apify Actors](https://apify.com/) into your CrewAI workflows.
|
||||
|
||||
## Description
|
||||
|
||||
ApifyActorsTool connects [Apify Actors](https://apify.com/), cloud-based programs for web scraping and automation, to your CrewAI workflows. You can extract data, crawl websites, and automate tasks, all without requiring infrastructure management.
|
||||
|
||||
**Key features**:
|
||||
- **Run Actors** directly, like the [RAG Web Browser](https://apify.com/apify/rag-web-browser), with CrewAI agents.
|
||||
- **Access real-time data** for tasks that need fresh web content or automation.
|
||||
|
||||
See the [Apify CrewAI documentation](https://docs.apify.com/platform/integrations/crewai) for a detailed integration guide.
|
||||
|
||||
## Installation
|
||||
|
||||
To use ApifyActorsTool, install the necessary packages and set up your Apify API token. Follow the [Apify API documentation](https://docs.apify.com/platform/integrations/api) for steps to obtain the token.
|
||||
|
||||
### Steps
|
||||
|
||||
1. **Install dependencies**
|
||||
Use pip to install `crewai[tools]` and `langchain-apify`:
|
||||
```bash
|
||||
pip install 'crewai[tools]' langchain-apify
|
||||
```
|
||||
Or, with `uv`:
|
||||
```bash
|
||||
uv pip install 'crewai[tools]' langchain-apify
|
||||
```
|
||||
|
||||
2. **Set your API token**
|
||||
Export the token as an environment variable:
|
||||
```bash
|
||||
export APIFY_API_TOKEN='your-api-token-here'
|
||||
```
|
||||
|
||||
## Usage example
|
||||
|
||||
Use ApifyActorsTool to run the [RAG Web Browser Actor](https://apify.com/apify/rag-web-browser) and perform a web search:
|
||||
|
||||
```python
|
||||
from crewai_tools import ApifyActorsTool
|
||||
|
||||
# Initialize the tool with an Apify Actor
|
||||
tool = ApifyActorsTool(actor_name="apify/rag-web-browser")
|
||||
|
||||
# Run the tool with input parameters
|
||||
results = tool.run(run_input={"query": "What is CrewAI?", "maxResults": 5})
|
||||
|
||||
# Process the results
|
||||
for result in results:
|
||||
print(f"URL: {result['metadata']['url']}")
|
||||
print(f"Content: {result.get('markdown', 'N/A')[:100]}...")
|
||||
```
|
||||
|
||||
### Expected output
|
||||
|
||||
Here is the output from running the code above:
|
||||
|
||||
```text
|
||||
URL: https://www.example.com/crewai-intro
|
||||
Content: CrewAI is a framework for building AI-powered workflows...
|
||||
URL: https://docs.crewai.com/
|
||||
Content: Official documentation for CrewAI...
|
||||
```
|
||||
|
||||
Experiment with other Actors from the [Apify Store](https://apify.com/store) by updating `actor_name` and `run_input` based on each Actor's input schema.
|
||||
|
||||
For an example of usage with agents, see the [CrewAI Apify Actor template](https://apify.com/templates/python-crewai).
|
||||
|
||||
## Configuration
|
||||
|
||||
ApifyActorsTool requires these inputs to work:
|
||||
|
||||
- **`actor_name`**
|
||||
The ID of the Apify Actor to run, e.g., `"apify/rag-web-browser"`. Browse options in the [Apify Store](https://apify.com/store).
|
||||
- **`run_input`**
|
||||
A dictionary of input parameters for the Actor. Examples:
|
||||
- For `apify/rag-web-browser`: `{"query": "search term", "maxResults": 5}`
|
||||
- See each Actor's [input schema](https://apify.com/apify/rag-web-browser/input-schema) for details.
|
||||
|
||||
## Resources
|
||||
|
||||
- **[Apify Platform](https://apify.com/)**: Dive into the Apify ecosystem.
|
||||
- **[RAG Web Browser Actor](https://apify.com/apify/rag-web-browser)**: Test this popular Actor for web data retrieval.
|
||||
- **[CrewAI Integration Guide](https://docs.apify.com/platform/integrations/crewai)**: Follow the official guide for Apify and CrewAI.
|
||||
@@ -9,34 +9,34 @@ if TYPE_CHECKING:
|
||||
class ApifyActorsTool(BaseTool):
|
||||
"""Tool that runs Apify Actors.
|
||||
|
||||
To use, you should have the environment variable `APIFY_API_TOKEN` set
|
||||
with your API key.
|
||||
To use, you should have the environment variable `APIFY_API_TOKEN` set
|
||||
with your API key.
|
||||
|
||||
For details, see https://docs.apify.com/platform/integrations/crewai
|
||||
For details, see https://docs.apify.com/platform/integrations/crewai
|
||||
|
||||
Args:
|
||||
actor_name (str): The name of the Apify Actor to run.
|
||||
*args: Variable length argument list passed to BaseTool.
|
||||
**kwargs: Arbitrary keyword arguments passed to BaseTool.
|
||||
Args:
|
||||
actor_name (str): The name of the Apify Actor to run.
|
||||
*args: Variable length argument list passed to BaseTool.
|
||||
**kwargs: Arbitrary keyword arguments passed to BaseTool.
|
||||
|
||||
Returns:
|
||||
List[Dict[str, Any]]: Results from the Actor execution.
|
||||
Returns:
|
||||
List[Dict[str, Any]]: Results from the Actor execution.
|
||||
|
||||
Raises:
|
||||
ValueError: If `APIFY_API_TOKEN` is not set or if the tool is not initialized.
|
||||
ImportError: If `langchain_apify` package is not installed.
|
||||
Raises:
|
||||
ValueError: If `APIFY_API_TOKEN` is not set or if the tool is not initialized.
|
||||
ImportError: If `langchain_apify` package is not installed.
|
||||
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from crewai_tools import ApifyActorsTool
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from crewai_tools import ApifyActorsTool
|
||||
|
||||
tool = ApifyActorsTool(actor_name="apify/rag-web-browser")
|
||||
tool = ApifyActorsTool(actor_name="apify/rag-web-browser")
|
||||
|
||||
results = tool.run(run_input={"query": "What is CrewAI?", "maxResults": 5})
|
||||
for result in results:
|
||||
print(f"URL: {result['metadata']['url']}")
|
||||
print(f"Content: {result.get('markdown', 'N/A')[:100]}...")
|
||||
"""
|
||||
results = tool.run(run_input={"query": "What is CrewAI?", "maxResults": 5})
|
||||
for result in results:
|
||||
print(f"URL: {result['metadata']['url']}")
|
||||
print(f"Content: {result.get('markdown', 'N/A')[:100]}...")
|
||||
"""
|
||||
actor_tool: '_ApifyActorsTool' = Field(description="Apify Actor Tool")
|
||||
|
||||
def __init__(
|
||||
Reference in New Issue
Block a user